[PATCH v6 09/18] ARM: LPAE: Page table maintenance for the 3-level format
From: Catalin Marinas
Date: Tue May 24 2011 - 17:43:07 EST
This patch modifies the pgd/pmd/pte manipulation functions to support
the 3-level page table format. Since there is no need for an 'ext'
argument to cpu_set_pte_ext(), this patch conditionally defines a
different prototype for this function when CONFIG_ARM_LPAE.
The patch also introduces the L_PGD_SWAPPER flag to mark pgd entries
pointing to pmd tables pre-allocated in the swapper_pg_dir and avoid
trying to free them at run-time. This flag is 0 with the classic page
table format.
Signed-off-by: Catalin Marinas <catalin.marinas@xxxxxxx>
---
arch/arm/include/asm/pgalloc.h | 24 +++++++++++++
arch/arm/include/asm/pgtable-3level.h | 5 +++
arch/arm/include/asm/pgtable.h | 62 ++++++++++++++++++++++++++++++++-
arch/arm/include/asm/proc-fns.h | 25 +++++++++++++
arch/arm/mm/ioremap.c | 8 +++--
arch/arm/mm/pgd.c | 51 +++++++++++++++++++++++++--
6 files changed, 167 insertions(+), 8 deletions(-)
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index 7418894..943504f 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -25,6 +25,26 @@
#define _PAGE_USER_TABLE (PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_USER))
#define _PAGE_KERNEL_TABLE (PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_KERNEL))
+#ifdef CONFIG_ARM_LPAE
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+ return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+ BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+ free_page((unsigned long)pmd);
+}
+
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+ set_pud(pud, __pud(__pa(pmd) | PMD_TYPE_TABLE));
+}
+
+#else /* !CONFIG_ARM_LPAE */
+
/*
* Since we have only two-level page tables, these are trivial
*/
@@ -32,6 +52,8 @@
#define pmd_free(mm, pmd) do { } while (0)
#define pud_populate(mm,pmd,pte) BUG()
+#endif /* CONFIG_ARM_LPAE */
+
extern pgd_t *pgd_alloc(struct mm_struct *mm);
extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
@@ -109,7 +131,9 @@ static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
{
pmdval_t pmdval = (pte + PTE_HWTABLE_OFF) | prot;
pmdp[0] = __pmd(pmdval);
+#ifndef CONFIG_ARM_LPAE
pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t));
+#endif
flush_pmd_entry(pmdp);
}
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 79bf0ac..a6261f5 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -99,4 +99,9 @@
#define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 3) << 2) /* normal inner write-back */
#define L_PTE_MT_MASK (_AT(pteval_t, 7) << 2)
+/*
+ * Software PGD flags.
+ */
+#define L_PGD_SWAPPER (_AT(pgdval_t, 1) << 55) /* swapper_pg_dir entry */
+
#endif /* _ASM_PGTABLE_3LEVEL_H */
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 95fefd9..1db9ad6 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -165,6 +165,31 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
/* to find an entry in a kernel page-table-directory */
#define pgd_offset_k(addr) pgd_offset(&init_mm, addr)
+#ifdef CONFIG_ARM_LPAE
+
+#define pud_none(pud) (!pud_val(pud))
+#define pud_bad(pud) (!(pud_val(pud) & 2))
+#define pud_present(pud) (pud_val(pud))
+
+#define pud_clear(pudp) \
+ do { \
+ *pudp = __pud(0); \
+ clean_pmd_entry(pudp); \
+ } while (0)
+
+#define set_pud(pudp, pud) \
+ do { \
+ *pudp = pud; \
+ flush_pmd_entry(pudp); \
+ } while (0)
+
+static inline pmd_t *pud_page_vaddr(pud_t pud)
+{
+ return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK);
+}
+
+#else /* !CONFIG_ARM_LPAE */
+
/*
* The "pud_xxx()" functions here are trivial when the pmd is folded into
* the pud: the pud entry is never bad, always exists, and can't be set or
@@ -176,15 +201,43 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
#define pud_clear(pudp) do { } while (0)
#define set_pud(pud,pudp) do { } while (0)
+#endif /* CONFIG_ARM_LPAE */
/* Find an entry in the second-level page table.. */
+#ifdef CONFIG_ARM_LPAE
+#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+ return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
+}
+#else
static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
{
return (pmd_t *)pud;
}
+#endif
#define pmd_none(pmd) (!pmd_val(pmd))
#define pmd_present(pmd) (pmd_val(pmd))
+
+#ifdef CONFIG_ARM_LPAE
+
+#define pmd_bad(pmd) (!(pmd_val(pmd) & 2))
+
+#define copy_pmd(pmdpd,pmdps) \
+ do { \
+ *pmdpd = *pmdps; \
+ flush_pmd_entry(pmdpd); \
+ } while (0)
+
+#define pmd_clear(pmdp) \
+ do { \
+ *pmdp = __pmd(0); \
+ clean_pmd_entry(pmdp); \
+ } while (0)
+
+#else /* !CONFIG_ARM_LPAE */
+
#define pmd_bad(pmd) (pmd_val(pmd) & 2)
#define copy_pmd(pmdpd,pmdps) \
@@ -201,6 +254,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
clean_pmd_entry(pmdp); \
} while (0)
+#endif /* CONFIG_ARM_LPAE */
+
static inline pte_t *pmd_page_vaddr(pmd_t pmd)
{
return __va(pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK);
@@ -233,9 +288,14 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
#define mk_pte(page,prot) pfn_pte(page_to_pfn(page), prot)
-#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
#define pte_clear(mm,addr,ptep) set_pte_ext(ptep, __pte(0), 0)
+#ifdef CONFIG_ARM_LPAE
+#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,__pte(pte_val(pte)|(ext)))
+#else
+#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
+#endif
+
#if __LINUX_ARM_ARCH__ < 6
static inline void __sync_icache_dcache(pte_t pteval)
{
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index 233dccd..3a68cd4 100644
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@@ -65,7 +65,11 @@ extern struct processor {
* Set a possibly extended PTE. Non-extended PTEs should
* ignore 'ext'.
*/
+#ifdef CONFIG_ARM_LPAE
+ void (*set_pte_ext)(pte_t *ptep, pte_t pte);
+#else
void (*set_pte_ext)(pte_t *ptep, pte_t pte, unsigned int ext);
+#endif
/* Suspend/resume */
unsigned int suspend_size;
@@ -79,7 +83,11 @@ extern void cpu_proc_fin(void);
extern int cpu_do_idle(void);
extern void cpu_dcache_clean_area(void *, int);
extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
+#ifdef CONFIG_ARM_LPAE
+extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte);
+#else
extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
+#endif
extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
#else
#define cpu_proc_init() processor._proc_init()
@@ -87,7 +95,11 @@ extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
#define cpu_reset(addr) processor.reset(addr)
#define cpu_do_idle() processor._do_idle()
#define cpu_dcache_clean_area(addr,sz) processor.dcache_clean_area(addr,sz)
+#ifdef CONFIG_ARM_LPAE
+#define cpu_set_pte_ext(ptep,pte) processor.set_pte_ext(ptep,pte)
+#else
#define cpu_set_pte_ext(ptep,pte,ext) processor.set_pte_ext(ptep,pte,ext)
+#endif
#define cpu_do_switch_mm(pgd,mm) processor.switch_mm(pgd,mm)
#endif
@@ -113,6 +125,18 @@ extern void cpu_resume(void);
#endif
+#ifdef CONFIG_ARM_LPAE
+#define cpu_get_pgd() \
+ ({ \
+ unsigned long pg, pg2; \
+ __asm__("mrrc p15, 0, %0, %1, c2" \
+ : "=r" (pg), "=r" (pg2) \
+ : \
+ : "cc"); \
+ pg &= ~(PTRS_PER_PGD*sizeof(pgd_t)-1); \
+ (pgd_t *)phys_to_virt(pg); \
+ })
+#else
#define cpu_get_pgd() \
({ \
unsigned long pg; \
@@ -121,6 +145,7 @@ extern void cpu_resume(void);
pg &= ~0x3fff; \
(pgd_t *)phys_to_virt(pg); \
})
+#endif
#endif
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index ab50627..6bdf42c 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -64,7 +64,7 @@ void __check_kvm_seq(struct mm_struct *mm)
} while (seq != init_mm.context.kvm_seq);
}
-#ifndef CONFIG_SMP
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
/*
* Section support is unsafe on SMP - If you iounmap and ioremap a region,
* the other CPUs will not see this change until their next context switch.
@@ -195,11 +195,13 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
unsigned long addr;
struct vm_struct * area;
+#ifndef CONFIG_ARM_LPAE
/*
* High mappings must be supersection aligned
*/
if (pfn >= 0x100000 && (__pfn_to_phys(pfn) & ~SUPERSECTION_MASK))
return NULL;
+#endif
/*
* Don't allow RAM to be mapped - this causes problems with ARMv6+
@@ -221,7 +223,7 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
return NULL;
addr = (unsigned long)area->addr;
-#ifndef CONFIG_SMP
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
if (DOMAIN_IO == 0 &&
(((cpu_architecture() >= CPU_ARCH_ARMv6) && (get_cr() & CR_XP)) ||
cpu_is_xsc3()) && pfn >= 0x100000 &&
@@ -292,7 +294,7 @@ EXPORT_SYMBOL(__arm_ioremap);
void __iounmap(volatile void __iomem *io_addr)
{
void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr);
-#ifndef CONFIG_SMP
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
struct vm_struct **p, *tmp;
/*
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index b2027c1..a3e78cc 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -10,6 +10,7 @@
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/highmem.h>
+#include <linux/slab.h>
#include <asm/pgalloc.h>
#include <asm/page.h>
@@ -17,6 +18,14 @@
#include "mm.h"
+#ifdef CONFIG_ARM_LPAE
+#define __pgd_alloc() kmalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL)
+#define __pgd_free(pgd) kfree(pgd)
+#else
+#define __pgd_alloc() (pgd_t *)__get_free_pages(GFP_KERNEL, 2)
+#define __pgd_free(pgd) free_pages((unsigned long)pgd, 2)
+#endif
+
/*
* need to get a 16k page for level 1
*/
@@ -27,7 +36,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
pmd_t *new_pmd, *init_pmd;
pte_t *new_pte, *init_pte;
- new_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL, 2);
+ new_pgd = __pgd_alloc();
if (!new_pgd)
goto no_pgd;
@@ -42,10 +51,25 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
clean_dcache_area(new_pgd, PTRS_PER_PGD * sizeof(pgd_t));
+#ifdef CONFIG_ARM_LPAE
+ /*
+ * Allocate PMD table for modules and pkmap mappings.
+ */
+ new_pud = pud_alloc(mm, new_pgd + pgd_index(MODULES_VADDR),
+ MODULES_VADDR);
+ if (!new_pud)
+ goto no_pud;
+
+ new_pmd = pmd_alloc(mm, new_pud, 0);
+ if (!new_pmd)
+ goto no_pmd;
+#endif
+
if (!vectors_high()) {
/*
* On ARM, first page must always be allocated since it
- * contains the machine vectors.
+ * contains the machine vectors. The vectors are always high
+ * with LPAE.
*/
new_pud = pud_alloc(mm, new_pgd, 0);
if (!new_pud)
@@ -74,7 +98,7 @@ no_pte:
no_pmd:
pud_free(mm, new_pud);
no_pud:
- free_pages((unsigned long)new_pgd, 2);
+ __pgd_free(new_pgd);
no_pgd:
return NULL;
}
@@ -111,5 +135,24 @@ no_pud:
pgd_clear(pgd);
pud_free(mm, pud);
no_pgd:
- free_pages((unsigned long) pgd_base, 2);
+#ifdef CONFIG_ARM_LPAE
+ /*
+ * Free modules/pkmap or identity pmd tables.
+ */
+ for (pgd = pgd_base; pgd < pgd_base + PTRS_PER_PGD; pgd++) {
+ if (pgd_none_or_clear_bad(pgd))
+ continue;
+ if (pgd_val(*pgd) & L_PGD_SWAPPER)
+ continue;
+ pud = pud_offset(pgd, 0);
+ if (pud_none_or_clear_bad(pud))
+ continue;
+ pmd = pmd_offset(pud, 0);
+ pud_clear(pud);
+ pmd_free(mm, pmd);
+ pgd_clear(pgd);
+ pud_free(mm, pud);
+ }
+#endif
+ __pgd_free(pgd_base);
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/